azure-monitor-query-py

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • Official SDK Installation: The skill instructs the installation of azure-monitor-query via pip. This is the official Microsoft library for interacting with Azure Monitor services. This is a standard and expected dependency for the skill's functionality.
  • Authentication and Resource Management: The skill emphasizes the use of DefaultAzureCredential, which avoids the need for hardcoded connection strings or API keys, and utilizes context managers to ensure deterministic cleanup of HTTP transports and sockets. These are recognized security and reliability best practices.
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process external data from Log Analytics workspaces.
  • Ingestion points: Data enters the agent's context through the response.tables and row objects returned by client.query_workspace in SKILL.md.
  • Boundary markers: The provided code snippets do not explicitly show boundary markers or delimiters for the queried log data.
  • Capability inventory: The skill performs data extraction, printing, and conversion to DataFrames (using pandas) within SKILL.md.
  • Sanitization: The snippets do not include explicit sanitization or filtering of the queried log content before it is processed or displayed. While this represents a theoretical surface where malicious log entries could influence agent behavior, it is inherent to the skill's primary purpose of log analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-monitor-query-py